Deep Learning – Image Denoising

---

Comparative Study of Deep Learning Algorithms for Atomic Force Microscope Image Denoising

Objective

Atomic force microscopy (AFM) enables direct visualisation of surface topography at the nanoscale. However, post-processing is generally required to obtain accurate, precise, and reliable AFM images owing to the presence of image artefacts. In this study, we compared and analysed state-of-the-art deep learning models, namely MPRNet, HINet, Uformer, and Restormer, with respect to denoising of AFM images containing four types of noise.

Data

Organic Electronic Morphology Dataset

Related Work

VDSR, UNet, REDNet

Proposed Method

We evaluated the PSNR and SSIM of the models used in previous studies, such as VDSR, UNet, REDNet, and UNET-REDNet, and SOTA models, such as MPRNet, HINet, Uformer, and Restormer.